[Bug 81735] [BSW]igt/gem_exec_lut_handle cost long time to execute sporadically

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=81735

--- Comment #3 from Guo Jinxian <jinxianx.guo at intel.com> ---
Created attachment 103431
  --> https://bugs.freedesktop.org/attachment.cgi?id=103431&action=edit
dmesg on -next-queued branch

(In reply to comment #2)
> (In reply to comment #1)
> > How does the pass compare? (i.e. please attach the good output and dmesg)
> 
> Here is the output on latest -next-queued which passed.
> 
> [root at x-bsw01 tests]# time ./gem_exec_lut_handle
> IGT-Version: 1.7-g4d4f4b2 (x86_64) (Linux:
> 3.16.0-rc4_drm-intel-next-queued_2b8ee5_20140725+ x86_64)
> relocation: buffers=   1: old=  20213 + 160.6*reloc, lut=  21170 +
> 150.9*reloc (ns)
> relocation: buffers=   2: old=  23548 + 160.3*reloc, lut=  26650 +
> 149.6*reloc (ns)
> relocation: buffers=   4: old=  23450 + 160.0*reloc, lut=  24112 +
> 150.5*reloc (ns)
> relocation: buffers=   8: old=  28316 + 159.0*reloc, lut=  30131 +
> 149.1*reloc (ns)
> relocation: buffers=  16: old=  29774 + 160.0*reloc, lut=  31269 +
> 150.0*reloc (ns)
> relocation: buffers=  32: old=  35678 + 161.4*reloc, lut=  35133 +
> 151.7*reloc (ns)
> relocation: buffers=  64: old=  60752 + 162.4*reloc, lut=  62951 +
> 151.1*reloc (ns)
> relocation: buffers= 128: old=  95711 + 172.6*reloc, lut=  94049 +
> 160.7*reloc (ns)
> relocation: buffers= 256: old= 188186 + 178.5*reloc, lut= 184888 +
> 165.0*reloc (ns)
> relocation: buffers= 512: old= 362717 + 195.3*reloc, lut= 356609 +
> 168.5*reloc (ns)
> relocation: buffers=1024: old= 752565 + 258.9*reloc, lut= 737432 +
> 204.8*reloc (ns)
> 
> relocation: buffers=2048: old=4130880 + 375.5*reloc, lut=4117357 +
> 279.1*reloc (ns)
> skip-relocs: buffers=   1: old=   7075 + 87.0*reloc, lut=   6909 +
> 80.3*reloc (ns)
> skip-relocs: buffers=   2: old=   7721 + 87.0*reloc, lut=   7554 +
> 80.3*reloc (ns)
> skip-relocs: buffers=   4: old=   8532 + 87.0*reloc, lut=   8321 +
> 80.3*reloc (ns)
> skip-relocs: buffers=   8: old=  10332 + 87.2*reloc, lut=  10062 +
> 80.5*reloc (ns)
> skip-relocs: buffers=  16: old=  14190 + 87.4*reloc, lut=  13790 +
> 80.7*reloc (ns)
> skip-relocs: buffers=  32: old=  22911 + 87.4*reloc, lut=  22027 +
> 80.8*reloc (ns)
> skip-relocs: buffers=  64: old=  43343 + 89.4*reloc, lut=  41712 +
> 82.4*reloc (ns)
> skip-relocs: buffers= 128: old=  94919 + 92.8*reloc, lut=  93175 +
> 83.8*reloc (ns)
> skip-relocs: buffers= 256: old= 186820 + 99.9*reloc, lut= 183693 +
> 88.6*reloc (ns)
> skip-relocs: buffers= 512: old= 361709 + 115.8*reloc, lut= 355697 +
> 92.4*reloc (ns)
> skip-relocs: buffers=1024: old= 743773 + 174.1*reloc, lut= 735623 +
> 126.8*reloc (ns)
> skip-relocs: buffers=2048: old=4132826 + 283.8*reloc, lut=4114821 +
> 194.7*reloc (ns)
> no-relocs: buffers=   1: old=   6812 + 30.2*reloc, lut=   6704 + 23.5*reloc
> (ns)
> no-relocs: buffers=   2: old=   7248 + 30.3*reloc, lut=   7071 + 23.6*reloc
> (ns)
> no-relocs: buffers=   4: old=   8168 + 30.3*reloc, lut=   7906 + 23.7*reloc
> (ns)
> no-relocs: buffers=   8: old=   9970 + 30.3*reloc, lut=   9437 + 23.7*reloc
> (ns)
> no-relocs: buffers=  16: old=  13394 + 30.6*reloc, lut=  13017 + 23.9*reloc
> (ns)
> no-relocs: buffers=  32: old=  21729 + 30.6*reloc, lut=  21105 + 24.0*reloc
> (ns)
> no-relocs: buffers=  64: old=  40860 + 31.5*reloc, lut=  39069 + 25.0*reloc
> (ns)
> no-relocs: buffers= 128: old=  90798 + 29.8*reloc, lut=  88936 + 22.9*reloc
> (ns)
> no-relocs: buffers= 256: old= 178076 + 29.7*reloc, lut= 174850 + 22.4*reloc
> (ns)
> no-relocs: buffers= 512: old= 343969 + 31.0*reloc, lut= 337410 + 22.4*reloc
> (ns)
> no-relocs: buffers=1024: old= 714549 + 46.5*reloc, lut= 704009 + 37.8*reloc
> (ns)
> no-relocs: buffers=2048: old=4040396 + 49.3*reloc, lut=4017948 + 37.6*reloc
> (ns)
> 
> real    8m19.540s
> user    0m18.975s
> sys     7m59.965s

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.freedesktop.org/archives/intel-gfx-bugs/attachments/20140725/4512be7e/attachment-0001.html>